{
  "dataset": "wiki",
  "questions": 600,
  "candidate_count_per_question": 10,
  "selection_rule": "same neural_evidence_graph_core.graph_arrays and graph_select as four new datasets: 0.4 * per-query minmax relevance + 0.5 * max selected-to-candidate directed title-body link + 0.2 * query-title match; no tuning, no query facets, no specialized presets",
  "embedding_source": "previously frozen/precomputed actual all-MiniLM-L6-v2 q and passage vectors; cosine recomputed",
  "crossencoder_source": "previously frozen/precomputed actual pretrained ms-marco-MiniLM-L6-v2 256-wordpiece query-passage logits, same ids",
  "complete_evidence_coverage_pct": {
    "dense_cosine": {
      "2": 24.83,
      "3": 34.17,
      "5": 52.33,
      "8": 81.5
    },
    "crossencoder": {
      "2": 33.83,
      "3": 44.5,
      "5": 58.67,
      "8": 79.33
    },
    "dense_graph": {
      "2": 61.5,
      "3": 68.33,
      "5": 93.0,
      "8": 98.33
    },
    "crossencoder_graph": {
      "2": 62.83,
      "3": 70.17,
      "5": 93.17,
      "8": 98.17
    }
  },
  "crossencoder_graph_vs_crossencoder_at3": {
    "diff_pp": 25.67,
    "ci95_pp": [
      22.17,
      29.33
    ],
    "wins": 159,
    "losses": 5,
    "ties": 436
  },
  "dense_graph_vs_dense_at3": {
    "diff_pp": 34.17,
    "ci95_pp": [
      30.0,
      38.0
    ],
    "wins": 209,
    "losses": 4,
    "ties": 387
  },
  "graph_link_present_pct": 81.67,
  "gold_support_count_distribution": {
    "2": 459,
    "4": 141
  },
  "timing": {
    "graph_feature_extraction_and_four_rankings_ms_per_question": 0.322,
    "graph_feature_extraction_and_four_rankings_total_s": 0.1933,
    "pretrained_crossencoder_scoring_ms_per_question_from_original_inference_run": 254.92,
    "cached_embedding_and_crossencoder_scores": true
  },
  "note": "This is an actual rerun of ranking/selection and evidence coverage from cached neural scores; scoring step was previously executed, not repeated. Scores are on the same selected 600 held-out question IDs."
}